SELECT customer_id, SUM(amount) AS total_spend
FROM orders
GROUP BY customer_id
ORDER BY total_spend DESC
LIMIT 5;

Explanation: Use GROUP BY to aggregate spend by customer, ORDER BY DESC to sort highest first, and LIMIT 5 to get top customers. This is a common business analytics question.

import pandas as pd

# Check for missing values
df.isnull().sum()

# Remove rows with missing values
df.dropna(inplace=True)

# Fill missing values with a specific value
df.fillna(0, inplace=True)

# Fill with mean/median for numeric columns
df['column'].fillna(df['column'].mean(), inplace=True)

# For categorical columns, fill with mode
df['category'].fillna(df['category'].mode()[0], inplace=True)

Explanation: Missing values are common in real-world data. Handling them properly is critical for accurate analysis. The approach depends on the nature of the data and the analysis goal.

WHERE filters rows before aggregation. It is used with SELECT, UPDATE, and DELETE statements. HAVING filters after aggregation. It is used with GROUP BY to filter on aggregate functions like SUM(), COUNT(), AVG().

Example:

-- WHERE filters individual rows
SELECT * FROM orders WHERE amount > 100;

-- HAVING filters groups after aggregation
SELECT customer_id, SUM(amount) AS total
FROM orders
GROUP BY customer_id
HAVING total > 1000;

import pandas as pd

# Inner join (common keys)
df_merged = pd.merge(df1, df2, on='key_column')

# Left join
df_merged = pd.merge(df1, df2, on='key_column', how='left')

# Right join
df_merged = pd.merge(df1, df2, on='key_column', how='right')

# Outer join (all keys)
df_merged = pd.merge(df1, df2, on='key_column', how='outer')

# Merge on different column names
df_merged = pd.merge(df1, df2, left_on='key1', right_on='key2')

Explanation: Merging is essential for combining data from multiple sources. The 'how' parameter determines which keys are included in the result.

Mean is the average of all values. It's sensitive to outliers.

Median is the middle value when data is sorted. It's robust to outliers.

Mode is the most frequent value in the dataset.

When to use: Use mean for normally distributed data. Use median for skewed data or when outliers are present. Use mode for categorical data.

A p-value is the probability of observing results as extreme as those observed, assuming the null hypothesis is true.

Interpretation:

• p < 0.05: Strong evidence against the null hypothesis (statistically significant).
• p > 0.05: Weak evidence against the null hypothesis (not statistically significant).
• p = 0.01: 1% chance the results are due to random chance.

Note: A small p-value doesn't necessarily mean practical significance — it just indicates statistical significance.

The Central Limit Theorem (CLT) states that the sampling distribution of the sample mean approaches a normal distribution as the sample size increases, regardless of the population distribution.

Why it's important:

• Enables hypothesis testing and confidence intervals using normal distribution.
• Allows generalization from sample to population.
• Validates many statistical methods even when the underlying data is not normally distributed.

Key insight: With a large enough sample size (typically n > 30), the CLT makes the normal distribution a powerful tool for statistical inference.

Dashboard: A visual display of the most important information needed to achieve one or more objectives. It's interactive, updated in real-time, and designed for monitoring and quick decision-making.

Report: A structured document that presents data in a static format. It's typically created periodically (weekly, monthly, quarterly) and is designed for in-depth analysis and record-keeping.

Key differences:

• Dashboards are interactive and dynamic; reports are static.
• Dashboards show real-time or near-real-time data; reports are historical.
• Dashboards are visual and concise; reports can be detailed and lengthy.

KPI (Key Performance Indicator): A measurable value that demonstrates how effectively a company is achieving key business objectives.

How to choose the right KPIs:

• Align with business goals: KPIs should measure progress toward strategic objectives.
• Be specific and measurable: KPIs should be quantifiable.
• Be actionable: KPIs should help drive decision-making and action.
• Be timely: KPIs should be tracked regularly to enable quick response.

Examples: Customer acquisition cost, customer lifetime value, conversion rate, churn rate, revenue growth.

Sample answer (STAR method):

Situation: Our e-commerce platform was experiencing a 15% drop in conversions. The marketing team was unsure if it was due to a recent website redesign or external factors.

Task: I was asked to analyze user behavior data to identify the root cause of the conversion drop.

Action: I analyzed web analytics data, user session recordings, and A/B testing results. I found that the new checkout flow had an extra step that was causing users to abandon their carts. I presented my findings with visual evidence to the product team.

Result: The product team reverted the checkout flow. Conversions recovered to previous levels and increased by 5% in the following month. The team now uses data-driven insights for all product changes.

SQL is the most important skill. Almost every data analytics interview includes SQL questions. Strong SQL skills are essential for data extraction and manipulation.

Practice SQL and Python daily, review statistics concepts, prepare your portfolio projects, and practice behavioral questions using the STAR method.

Be honest and say "I don't know, but here's how I would approach it." Show your problem-solving process — interviewers value this more than a perfect answer.

Yes — bring your laptop and be ready to show 1-2 projects. Walk through your process, challenges, and results. This is often more impressive than a perfect answer to a question.